From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> To: Quan Xu <quan.xu03@gmail.com> Cc: kvm@vger.kernel.org, linux-doc@vger.kernel.org, linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org, virtualization@lists.linux-foundation.org, x86@kernel.org, xen-devel@lists.xenproject.org, Yang Zhang <yang.zhang.wz@gmail.com> Subject: Re: [Xen-devel] [PATCH RFC v3 0/6] x86/idle: add halt poll support Date: Wed, 15 Nov 2017 16:31:31 -0500 [thread overview] Message-ID: <20171115213131.GB21113@char.us.oracle.com> (raw) In-Reply-To: <1510567565-5118-1-git-send-email-quan.xu0@gmail.com> On Mon, Nov 13, 2017 at 06:05:59PM +0800, Quan Xu wrote: > From: Yang Zhang <yang.zhang.wz@gmail.com> > > Some latency-intensive workload have seen obviously performance > drop when running inside VM. The main reason is that the overhead > is amplified when running inside VM. The most cost I have seen is > inside idle path. Meaning an VMEXIT b/c it is an 'halt' operation ? And then going back in guest (VMRESUME) takes time. And hence your latency gets all whacked b/c of this? So if I understand - you want to use your _full_ timeslice (of the guest) without ever (or as much as possible) to go in the hypervisor? Which means in effect you don't care about power-saving or CPUfreq savings, you just want to eat the full CPU for snack? > > This patch introduces a new mechanism to poll for a while before > entering idle state. If schedule is needed during poll, then we > don't need to goes through the heavy overhead path. Schedule of what? The guest or the host?
WARNING: multiple messages have this Message-ID (diff)
From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> To: Quan Xu <quan.xu03@gmail.com> Cc: Yang Zhang <yang.zhang.wz@gmail.com>, kvm@vger.kernel.org, linux-doc@vger.kernel.org, x86@kernel.org, linux-kernel@vger.kernel.org, virtualization@lists.linux-foundation.org, linux-fsdevel@vger.kernel.org, xen-devel@lists.xenproject.org Subject: Re: [Xen-devel] [PATCH RFC v3 0/6] x86/idle: add halt poll support Date: Wed, 15 Nov 2017 16:31:31 -0500 [thread overview] Message-ID: <20171115213131.GB21113@char.us.oracle.com> (raw) In-Reply-To: <1510567565-5118-1-git-send-email-quan.xu0@gmail.com> On Mon, Nov 13, 2017 at 06:05:59PM +0800, Quan Xu wrote: > From: Yang Zhang <yang.zhang.wz@gmail.com> > > Some latency-intensive workload have seen obviously performance > drop when running inside VM. The main reason is that the overhead > is amplified when running inside VM. The most cost I have seen is > inside idle path. Meaning an VMEXIT b/c it is an 'halt' operation ? And then going back in guest (VMRESUME) takes time. And hence your latency gets all whacked b/c of this? So if I understand - you want to use your _full_ timeslice (of the guest) without ever (or as much as possible) to go in the hypervisor? Which means in effect you don't care about power-saving or CPUfreq savings, you just want to eat the full CPU for snack? > > This patch introduces a new mechanism to poll for a while before > entering idle state. If schedule is needed during poll, then we > don't need to goes through the heavy overhead path. Schedule of what? The guest or the host?
next prev parent reply other threads:[~2017-11-15 21:31 UTC|newest] Thread overview: 99+ messages / expand[flat|nested] mbox.gz Atom feed top 2017-11-13 10:05 [PATCH RFC v3 0/6] x86/idle: add halt poll support Quan Xu 2017-11-13 10:06 ` [PATCH RFC v3 1/6] x86/paravirt: Add pv_idle_ops to paravirt ops Quan Xu 2017-11-13 10:53 ` Juergen Gross 2017-11-13 11:09 ` Wanpeng Li 2017-11-13 11:09 ` Wanpeng Li 2017-11-13 11:09 ` Wanpeng Li 2017-11-13 11:09 ` Wanpeng Li 2017-11-14 7:02 ` Quan Xu 2017-11-14 7:02 ` Quan Xu 2017-11-14 7:02 ` Quan Xu 2017-11-14 7:12 ` Wanpeng Li 2017-11-14 7:12 ` Wanpeng Li 2017-11-14 8:15 ` Quan Xu 2017-11-14 8:15 ` Quan Xu 2017-11-14 8:15 ` Quan Xu 2017-11-14 8:22 ` Wanpeng Li 2017-11-14 8:22 ` Wanpeng Li 2017-11-14 8:22 ` Wanpeng Li 2017-11-14 8:22 ` Wanpeng Li 2017-11-14 10:23 ` Quan Xu 2017-11-14 10:23 ` Quan Xu 2017-11-14 10:23 ` Quan Xu 2017-11-14 10:23 ` Quan Xu 2017-11-14 8:22 ` Wanpeng Li 2017-11-14 8:15 ` Quan Xu 2017-11-14 7:12 ` Wanpeng Li 2017-11-14 7:12 ` Wanpeng Li 2017-11-14 7:30 ` Juergen Gross 2017-11-14 7:30 ` Juergen Gross 2017-11-14 9:38 ` Quan Xu 2017-11-14 10:27 ` Juergen Gross 2017-11-14 11:43 ` Quan Xu 2017-11-14 11:43 ` Quan Xu 2017-11-14 11:43 ` Quan Xu 2017-11-14 11:58 ` Juergen Gross 2017-11-14 11:58 ` Juergen Gross 2017-11-14 11:58 ` Juergen Gross 2017-11-14 10:27 ` Juergen Gross 2017-11-14 10:27 ` Juergen Gross 2017-11-14 9:38 ` Quan Xu 2017-11-14 9:38 ` Quan Xu 2017-11-14 7:30 ` Juergen Gross 2017-11-13 10:53 ` Juergen Gross 2017-11-13 10:53 ` Juergen Gross 2017-11-13 10:06 ` Quan Xu 2017-11-13 10:06 ` [PATCH RFC v3 2/6] KVM guest: register kvm_idle_poll for pv_idle_ops Quan Xu 2017-11-13 10:06 ` Quan Xu 2017-11-13 10:06 ` [PATCH RFC v3 3/6] sched/idle: Add a generic poll before enter real idle path Quan Xu 2017-11-15 12:11 ` Peter Zijlstra 2017-11-15 12:11 ` Peter Zijlstra 2017-11-15 22:03 ` Thomas Gleixner 2017-11-15 22:03 ` Thomas Gleixner 2017-11-15 22:03 ` Thomas Gleixner 2017-11-16 8:45 ` Peter Zijlstra 2017-11-16 8:45 ` Peter Zijlstra 2017-11-16 8:58 ` Thomas Gleixner 2017-11-16 8:58 ` Thomas Gleixner 2017-11-16 8:58 ` Thomas Gleixner 2017-11-16 9:29 ` Quan Xu 2017-11-16 9:29 ` Quan Xu 2017-11-16 9:47 ` Thomas Gleixner 2017-11-16 9:47 ` Thomas Gleixner 2017-11-16 9:47 ` Thomas Gleixner 2017-11-16 9:29 ` Quan Xu 2017-11-16 8:45 ` Peter Zijlstra 2017-11-16 9:12 ` Quan Xu 2017-11-16 9:45 ` Daniel Lezcano 2017-11-20 7:05 ` Quan Xu 2017-11-20 7:05 ` Quan Xu 2017-11-20 18:01 ` Daniel Lezcano 2017-11-20 18:01 ` Daniel Lezcano 2017-11-20 18:01 ` Daniel Lezcano 2017-11-20 7:05 ` Quan Xu 2017-11-16 9:45 ` Daniel Lezcano 2017-11-16 9:45 ` Daniel Lezcano 2017-11-16 9:53 ` Thomas Gleixner 2017-11-16 9:53 ` Thomas Gleixner 2017-11-17 11:23 ` Quan Xu 2017-11-17 11:23 ` Quan Xu 2017-11-17 11:23 ` Quan Xu 2017-11-17 11:36 ` Thomas Gleixner 2017-11-17 11:36 ` Thomas Gleixner 2017-11-17 11:36 ` Thomas Gleixner 2017-11-17 11:36 ` Thomas Gleixner 2017-11-17 12:21 ` Quan Xu 2017-11-17 12:21 ` Quan Xu 2017-11-17 12:21 ` Quan Xu 2017-11-17 12:21 ` Quan Xu 2017-11-16 9:53 ` Thomas Gleixner 2017-11-16 9:12 ` Quan Xu 2017-11-16 9:12 ` Quan Xu 2017-11-15 12:11 ` Peter Zijlstra 2017-11-13 10:06 ` Quan Xu 2017-11-15 21:31 ` [PATCH RFC v3 0/6] x86/idle: add halt poll support Konrad Rzeszutek Wilk 2017-11-15 21:31 ` Konrad Rzeszutek Wilk [this message] 2017-11-15 21:31 ` [Xen-devel] " Konrad Rzeszutek Wilk 2017-11-20 7:18 ` Quan Xu 2017-11-20 7:18 ` Quan Xu 2017-11-20 7:18 ` Quan Xu
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20171115213131.GB21113@char.us.oracle.com \ --to=konrad.wilk@oracle.com \ --cc=kvm@vger.kernel.org \ --cc=linux-doc@vger.kernel.org \ --cc=linux-fsdevel@vger.kernel.org \ --cc=linux-kernel@vger.kernel.org \ --cc=quan.xu03@gmail.com \ --cc=virtualization@lists.linux-foundation.org \ --cc=x86@kernel.org \ --cc=xen-devel@lists.xenproject.org \ --cc=yang.zhang.wz@gmail.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.